Advances, Systems and Applications
Table 6 Merits and demerits of anomaly-based detection techniques
Approach | Advantages | Disadvantages |
|---|---|---|
Data mining | + The models are automatically generated. + It can be used in variety of situations. + Appropriate for use with online datasets. | - It depends on historical data. - It is based on complex algorithms. |
Machine learning | + High accurate detection. + It can be used to handle large amounts of data. | - Requires training data. - Extensive training time |
Statistical-based model | + Appropriate for use with online datasets. + Simplicity of the system. | - It is based on previous behaviour. - The accuracy of detection is determined by statistical processes. |
Rule-based model | + It is appropriate for online datasets. + Simplicity of the system. | - System is based on a set of rules. - There is a high risk of false positives rate. |